基于YOLOv3和OHEM的门机歪拉斜吊检测系统

Inclined Pulling and Hoisting Detection System of Gantry Crane Based on YOLOv3 with OHEM

防止歪拉斜吊对保障门机(又称龙门吊)安全工作有重要意义,提出了一种基于YOLOv3和OHEM的门机歪拉斜吊检测系统。该系统采用YOLOv3和SSD来识别目标,同时采用OHEM来解决数据集中简单样本和困难样本之间的不平衡问题。在检测过程中,结合定义的斜度角和歪度角公式判断是否超过阈值。实验结果表明,该检测系统具有良好的准确性和鲁棒性。

The prevention of inclined pulling and hoisting cranes is of great significance to guarantee the safe operation of gantry crane. In this paper, aninclined pulling and hoisting detection system of gantry crane based on YOLOv3 with OHEM is presented. The system employs YOLOv3 and SSD to identify targets. Meantime,online hard example mining(OHEM)is adopted to solve the imbalance between simple samples and hard samples in dataset. In the detection process, it combines the defined slant angle formula to distinguish whether the threshold is exceeded. The experimental results show that the detection system has good accuracy and robustness.